Unverified50% confidenceBenchmarkExact time
In GPT Researcher's experiments, the decision model Jev resulted in 73% of retrieved context being judged as relevant.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
9/30/2026
First Seen
Valid until: 12/29/2026
Sources
Related Entities
Related Claims
UnverifiedIn GPT Researcher's experiments, the decision-based approach improved the proportion of effective context by approximately 27 percentage points compared to traditional embedding retrieval.69% similarUnverified斯坦福的一项研究发现，71%人们向ChatGPT提出的问题可以由本地运行的模型来回答68% similarUnverifiedGPT-4 as a judge can achieve over 80% agreement with human evaluations, but exhibits systematic issues such as position bias, verbosity bias, and self-preference.66% similarUnverifiedIn experiments based on the Banking77 dataset, the BGE-small + logistic regression combination achieved 93.3% accuracy, while Jev achieved only 83.2%.63% similarUnverifiedJev can support confidence-based tiered decision-making: automatically execute above 90%, transfer to human review between 60% and 90%, and do not execute below 60%.62% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/960482API
curl https://kongchang.com/api/v1/knowledge/claims/960482MCP
get_claim(id=960482)